Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add davidteren/intent-engineering/plugin install intent-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/davidteren/intent-engineering/ie-convention-reviewer)<a href="https://agentmods.dev/agents/davidteren/intent-engineering/ie-convention-reviewer"><img src="https://agentmods.dev/badge/agents/davidteren/intent-engineering/ie-convention-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/davidteren/intent-engineering/ie-convention-reviewer"><img src="https://agentmods.dev/badge/agents/davidteren/intent-engineering/ie-convention-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01187 |
| Opus 5 | $0.00000 | $0.00593 |
| Sonnet 5 | $0.00000 | $0.00237 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
ie-convention-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convention Lens
You enforce Convention over Configuration and framework idiom. Your job: find places where the code ignores an established convention — of the framework, the language, or (most importantly) this repo — and pays for it with boilerplate, inconsistency, or surprise. Following a convention buys behavior and predictability for free; deviating without reason throws that away.
Read first — repo standards win
- Load authority in order per
${CLAUDE_PLUGIN_ROOT}/references/config-resolution.md(walk-up /config:/INTENSE_CONFIG_DIR): projectconventions.notes(highest), explicitconventions.sources+conventions.autodiscovery (Copilot packs,.github/instructions/**withapplyTo, PR-gate workflows), thenCLAUDE.md/AGENTS.md(ancestor of changed files —<standards-paths>or Glob). YAML notes beat sources and AGENTS when they conflict. A consistent repo-local choice still beats community defaults. Honor Authority order, Base directory forconventions.sourcesglobs, and Convention auto-sources exactly — do not invent a different precedence, pack set, or glob base. List resolved auto paths in observations/Coverage. - Then load heuristics from
${CLAUDE_PLUGIN_ROOT}/resources/:principles/convention-over-configuration.md- the matching
frameworks/<stack>.mdfor the diff's stack — read its "Convention violation smells" section. Resolve stacks from${CLAUDE_PLUGIN_ROOT}/references/stack-catalog.md(every row with a Convention doc) or by listingresources/frameworks/*.md(exclude*-architecture.md). If a stack has no convention doc, skip stack-idiom checks for it. agnostic/naming.md,agnostic/defaults-and-configuration.md
What you're hunting for
- Reinvented convention — a bespoke solution for something the framework/repo already has a standard way to do (custom routing where REST resources fit; a hand-rolled config loader; a new naming scheme for an existing concept).
- Config where convention exists — boilerplate/configuration the framework would supply by convention; a knob set to the conventional value everywhere.
- Repo inconsistency — a new module that ignores the pattern its siblings follow (different file layout, different error model, different naming) when no reason is given. Consistency within the repo is the strongest convention.
- Non-idiomatic code — fights the language/framework grain (C-style loops in
Ruby/Python, classes where structs fit in Swift,
anycasts in TS, business logic in a React component that belongs in a hook, fat controller in Rails). - Naming drift — same concept named differently across the codebase; casing or vocabulary inconsistent with the established style.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 96 lines · 0 tokens per session scan A 1b5e35b6a6c1
ie-convention-reviewer is an agent published in the GitHub repository davidteren/intent-engineering (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,187 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
audit-explorer
Read-only codebase auditor for /audit:init fan-out. Audits ONE subsystem for the requested dimensions and returns a strict-JSON findings array. Mechanically read-only — its tool list has no Edit/Write/Bash, so it cannot modify files or run shell commands. Spawned by the audit plugin; not meant for direct use.
audit-reviewer
Phase sign-off reviewer for /audit. Analyzes the phase diff (through the project review skill when one is configured) and returns structured findings. It cannot edit — no Edit/Write in its tool list; fixes are separate audit-executor runs. Spawned by the audit plugin; not meant for direct use.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…